Lab 5

library(tidyverse)
library(completejourney)

transactions <- transactions_sample

Plot 1 - What number of kids in a married household buys the most fruit?

transactions %>%
  inner_join(products, by = "product_id") %>%
  filter(str_detect(product_category, regex("FRUIT", ignore_case = TRUE))) %>%
  inner_join(demographics, by = "household_id") %>%
  filter(marital_status == "Married") %>%
  group_by(kids_count) %>%
  mutate(total_sales = sum(sales_value, na.rm = TRUE)) %>%
  ggplot(aes(x = kids_count, y = total_sales)) +
    geom_col() +
    scale_x_discrete("Number of Kids in Married Household") +
    scale_y_continuous("Total Fruit Sales", label = scales::dollar) +
    ggtitle("What number of kids in a married household buys the most fruit?", 
          subtitle = "Married households with no kids buy the most fruit")

Plot 2 - What month are married households with no kids buying the most fruit?

transactions %>%
  inner_join(products, by = "product_id") %>%
  filter(str_detect(product_category, regex("FRUIT", ignore_case = TRUE))) %>%
  inner_join(demographics, by = "household_id") %>%
  filter(marital_status == "Married", kids_count == "0") %>%
  mutate(month = month(transaction_timestamp, label = TRUE)) %>%
  group_by(month) %>%
  mutate(total_sales = sum(sales_value, na.rm = TRUE)) %>%
  ggplot(aes(x = month, y = total_sales)) +
    geom_col() +
    scale_x_discrete("Month") +
    scale_y_continuous("Total Fruit Sales", label = scales::dollar) +
    ggtitle("What month are married households with no kids buying the most fruit?", 
            subtitle = "Married households with no kids buy the most fruit in August")

Plot 3 - Who’s Buying Vitamins?

products %>%
  filter(str_detect(product_category, regex("VITAMIN", ignore_case = TRUE))) %>%
  inner_join(transactions, by = "product_id") %>%
  inner_join(demographics, by = "household_id") %>%
  group_by(age, income) %>%
  mutate(total_sales = sum(sales_value, na.rm = TRUE)) %>%
  ggplot(aes(x = age, y = total_sales)) +
    geom_col() +
    facet_wrap(~income) +
    scale_x_discrete("Age") +
    scale_y_continuous("Total Vitamin Sales", label = scales::dollar) +
    ggtitle("Who's Buying Vitamins?", 
            subtitle = "People who are 45-54 years old with income 50-74K are buying the most vitamins")